Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 862 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.6462. Min Act: -0.1700
Data Index: 5743718 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.6113. Min Act: -0.1700
Data Index: 1209204 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.5851. Min Act: -0.1700
Data Index: 4435620 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.5589. Min Act: -0.1700
Data Index: 2587213 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.5414. Min Act: -0.1698
Data Index: 2879708 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.5326. Min Act: -0.1700
Data Index: 6565802 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.5326. Min Act: -0.1700
Data Index: 6573356 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.5238. Min Act: -0.1700
Data Index: 4789204 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.5151. Min Act: -0.1700
Data Index: 184608 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.5238. Min Act: -0.1700
Data Index: 1017955 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.5063. Min Act: -0.1700
Data Index: 5090318 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.5151. Min Act: -0.1700
Data Index: 2896795 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.5151. Min Act: -0.1700
Data Index: 68964 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.5151. Min Act: -0.1700
Data Index: 2485121 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.5238. Min Act: -0.1700
Data Index: 5060407 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.5151. Min Act: -0.1700
Data Index: 8633705 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.5063. Min Act: -0.1699
Data Index: 7249306 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.5063. Min Act: -0.1699
Data Index: 7311564 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.5063. Min Act: -0.1700
Data Index: 8038076 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6462. Min Range: -1.6462
Max Act: 1.5151. Min Act: -0.1700
Data Index: 4852295 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19